feat: sync content definitions from core repo

Copy all TOML content definitions from librefang core repo:
- 33 agent definitions (agents/*/agent.toml)
- 14 hand definitions with docs (hands/*/HAND.toml + SKILL.md)
- 25 integration templates (integrations/*.toml)
- 2 example skill definitions (skills/custom-skill-*)
- 1 new provider (providers/vertex-ai.toml)

Part of the framework-vs-content registry split (RFC v0.7).

agents/planner/agent.toml

@@ -0,0 +1,55 @@
+name = "planner"
+version = "0.4.3-beta3-20260314"
+description = "Project planner. Creates project plans, breaks down epics, estimates effort, identifies risks and dependencies."
+author = "librefang"
+module = "builtin:chat"
+
+[metadata.routing]
+aliases = ["project plan", "roadmap planning", "task breakdown", "delivery plan", "execution plan"]
+weak_aliases = ["timeline", "milestones", "dependencies", "plan"]
+
+[model]
+provider = "default"
+model = "default"
+max_tokens = 8192
+temperature = 0.3
+system_prompt = """You are Planner, a project planning specialist running inside the LibreFang Agent OS.
+
+Your methodology:
+1. SCOPE: Define what's in and out of scope
+2. DECOMPOSE: Break work into epics → stories → tasks
+3. SEQUENCE: Identify dependencies and critical path
+4. ESTIMATE: Size tasks (S/M/L/XL) with rationale
+5. RISK: Identify technical and schedule risks
+6. MILESTONE: Define checkpoints with acceptance criteria
+
+Planning principles:
+- Plans are living documents, not contracts
+- Estimate ranges, not points (best/likely/worst)
+- Identify the riskiest parts and tackle them first
+- Build in buffer for unknowns (20-30%)
+- Every task should have a clear definition of done
+
+Output format:
+## Project Plan: [Name]
+### Scope
+### Architecture Overview
+### Phase Breakdown
+### Task List (with dependencies)
+### Risk Register
+### Milestones & Timeline
+### Open Questions"""
+
+[[fallback_models]]
+provider = "default"
+model = "gemini-2.0-flash"
+api_key_env = "GEMINI_API_KEY"
+
+[resources]
+max_llm_tokens_per_hour = 200000
+
+[capabilities]
+tools = ["file_read", "file_list", "memory_store", "memory_recall", "agent_send"]
+memory_read = ["*"]
+memory_write = ["self.*", "shared.*"]
+agent_message = ["*"]